Revision 0f640dca08330dfc7820d610578e5935b5e654b2 authored by Mike Snitzer on 31 January 2013, 14:11:14 UTC, committed by Alasdair G Kergon on 31 January 2013, 14:11:14 UTC
thin_io_hints() is blindly copying the queue limits from the thin-pool
which can lead to incorrect limits being set. The fix here simply
deletes the thin_io_hints() hook which leaves the existing stacking
infrastructure to set the limits correctly.
When a thin-pool uses an MD device for the data device a thin device
from the thin-pool must respect MD's constraints about disallowing a bio
from spanning multiple chunks. Otherwise we can see problems. If the raid0
chunksize is 1152K and thin-pool chunksize is 256K I see the following
md/raid0 error (with extra debug tracing added to thin_endio) when
mkfs.xfs is executed against the thin device:
md/raid0:md99: make_request bug: can't convert block across chunks or bigger than 1152k 6688 127
device-mapper: thin: bio sector=2080 err=-5 bi_size=130560 bi_rw=17 bi_vcnt=32 bi_idx=0
This extra DM debugging shows that the failing bio is spanning across
the first and second logical 1152K chunk (sector 2080 + 255 takes the
bio beyond the first chunk's boundary of sector 2304). So the bio
splitting that DM is doing clearly isn't respecting the MD limits.
max_hw_sectors_kb is 127 for both the thin-pool and thin device
(queue_max_hw_sectors returns 255 so we'll excuse sysfs's lack of
precision). So this explains why bi_size is 130560.
But the thin device's max_hw_sectors_kb should be 4 (PAGE_SIZE) given
that it doesn't have a .merge function (for bio_add_page to consult
indirectly via dm_merge_bvec) yet the thin-pool does sit above an MD
device that has a compulsory merge_bvec_fn. This scenario is exactly
why DM must resort to sending single PAGE_SIZE bios to the underlying
layer. Some additional context for this is available in the header for
commit 8cbeb67a ("dm: avoid unsupported spanning of md stripe boundaries").
Long story short, the reason a thin device doesn't properly get
configured to have a max_hw_sectors_kb of 4 (PAGE_SIZE) is that
thin_io_hints() is blindly copying the queue limits from the thin-pool
device directly to the thin device's queue limits.
Fix this by eliminating thin_io_hints. Doing so is safe because the
block layer's queue limits stacking already enables the upper level thin
device to inherit the thin-pool device's discard and minimum_io_size and
optimal_io_size limits that get set in pool_io_hints. But avoiding the
queue limits copy allows the thin and thin-pool limits to be different
where it is important, namely max_hw_sectors_kb.
Reported-by: Daniel Browning <db@kavod.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
1 parent 949db15
pgtable-generic.c
/*
* mm/pgtable-generic.c
*
* Generic pgtable methods declared in asm-generic/pgtable.h
*
* Copyright (C) 2010 Linus Torvalds
*/
#include <linux/pagemap.h>
#include <asm/tlb.h>
#include <asm-generic/pgtable.h>
#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
/*
* Only sets the access flags (dirty, accessed), as well as write
* permission. Furthermore, we know it always gets set to a "more
* permissive" setting, which allows most architectures to optimize
* this. We return whether the PTE actually changed, which in turn
* instructs the caller to do things like update__mmu_cache. This
* used to be done in the caller, but sparc needs minor faults to
* force that call on sun4c so we changed this macro slightly
*/
int ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
pte_t entry, int dirty)
{
int changed = !pte_same(*ptep, entry);
if (changed) {
set_pte_at(vma->vm_mm, address, ptep, entry);
flush_tlb_fix_spurious_fault(vma, address);
}
return changed;
}
#endif
#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
int pmdp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
pmd_t entry, int dirty)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
int changed = !pmd_same(*pmdp, entry);
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
if (changed) {
set_pmd_at(vma->vm_mm, address, pmdp, entry);
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
}
return changed;
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
BUG();
return 0;
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
}
#endif
#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
int ptep_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep)
{
int young;
young = ptep_test_and_clear_young(vma, address, ptep);
if (young)
flush_tlb_page(vma, address);
return young;
}
#endif
#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
int pmdp_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp)
{
int young;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
#else
BUG();
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
young = pmdp_test_and_clear_young(vma, address, pmdp);
if (young)
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
return young;
}
#endif
#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
pte_t *ptep)
{
pte_t pte;
pte = ptep_get_and_clear((vma)->vm_mm, address, ptep);
if (pte_accessible(pte))
flush_tlb_page(vma, address);
return pte;
}
#endif
#ifndef __HAVE_ARCH_PMDP_CLEAR_FLUSH
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
pmd_t pmdp_clear_flush(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
pmd_t pmd;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
pmd = pmdp_get_and_clear(vma->vm_mm, address, pmdp);
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
return pmd;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
#ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
pmd_t pmd = pmd_mksplitting(*pmdp);
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
set_pmd_at(vma->vm_mm, address, pmdp, pmd);
/* tlb flush only to serialize against gup-fast */
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
{
assert_spin_locked(&mm->page_table_lock);
/* FIFO */
if (!mm->pmd_huge_pte)
INIT_LIST_HEAD(&pgtable->lru);
else
list_add(&pgtable->lru, &mm->pmd_huge_pte->lru);
mm->pmd_huge_pte = pgtable;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/* no "address" argument so destroys page coloring of some arch */
pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm)
{
pgtable_t pgtable;
assert_spin_locked(&mm->page_table_lock);
/* FIFO */
pgtable = mm->pmd_huge_pte;
if (list_empty(&pgtable->lru))
mm->pmd_huge_pte = NULL;
else {
mm->pmd_huge_pte = list_entry(pgtable->lru.next,
struct page, lru);
list_del(&pgtable->lru);
}
return pgtable;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
#ifndef __HAVE_ARCH_PMDP_INVALIDATE
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(*pmdp));
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
Computing file changes ...
